ef4a82eed0
scripts/run_tests.sh now runs pytest-xdist -n <N> --dist loadfile as the single canonical path on every OS (Linux and Windows CI lanes both use it). The per-file subprocess model (run_tests_parallel.py, and the interim run_xdist.sh experiment) is deleted along with its two self-tests: persistent xdist workers pay the interpreter+import wall once per worker instead of once per file (~0.5-1.5s x ~3400 files was a ~6-minute floor on Windows), and --dist loadfile pins a file's tests to ONE worker, bounding state pollution to co-scheduled files — which is exactly the class of flake we are now committing to fix properly. The serial process-killer quarantine phase is dropped too. It existed to keep process-tree-sweep tests from killing sibling xdist workers; the durable fix belongs in those tests (sweeps must target their own children, not enumerate every python process), and keeping a divergent two-phase path would hide that work. Kept from the old wrapper: hermetic env -i scrubbing, Windows location-var forwarding, venv probing, bytecode pre-compile, -m 'not integration', and the HERMES_TEST_IMAGE docker-knob allowlist. HERMES_TEST_FILE_TIMEOUT/FILE_RETRIES/SLICE go away with the runner they parameterized; -j/HERMES_TEST_WORKERS now map to xdist -n (Linux CI pins 96, Windows 32, default auto). Docs updated to match: AGENTS.md (runner contract, flake policy, isolation section), CONTRIBUTING.md, tests/conftest.py comments, classify_changes docstring + its lane expectation (a .sh runner no longer trips the supply-chain scan lane), comfyui README, hermes-agent contributor guide, debugpy skill and its website doc.
172 lines
7.7 KiB
Bash
Executable File
172 lines
7.7 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Canonical test runner for hermes-agent. Run this instead of calling
|
|
# `pytest` directly to guarantee your local run matches CI behavior.
|
|
#
|
|
# What this script enforces:
|
|
# * pytest-xdist with --dist loadfile — each test FILE's tests all run on
|
|
# ONE worker, so file-internal ordering is preserved and cross-file
|
|
# pollution is bounded to files co-scheduled on a worker. Persistent
|
|
# workers also pay the interpreter+import wall (~0.5-1.5s on Windows)
|
|
# once per worker instead of once per file.
|
|
# * TZ=UTC, LANG=C.UTF-8, PYTHONHASHSEED=0 (deterministic)
|
|
# * Env vars blanked (conftest.py also does this, but this
|
|
# is belt-and-suspenders for anyone running pytest outside our
|
|
# conftest path — e.g. on a single file)
|
|
# * Proper venv activation (probes .venv, venv, then ~/.hermes/...)
|
|
#
|
|
# Usage:
|
|
# scripts/run_tests.sh # full suite
|
|
# scripts/run_tests.sh -j 4 # cap worker count
|
|
# scripts/run_tests.sh tests/agent/ # discover only here
|
|
# scripts/run_tests.sh tests/agent/ tests/acp/ # multiple roots
|
|
# scripts/run_tests.sh tests/foo.py # single file
|
|
# scripts/run_tests.sh tests/foo.py -q # path + bare pytest flag
|
|
# scripts/run_tests.sh tests/foo.py -v --tb=long # bare flags "just work"
|
|
# scripts/run_tests.sh -k 'pattern' # value flags pass through too
|
|
#
|
|
# Bare pytest flags (anything starting with '-' that isn't -j/--jobs) are
|
|
# forwarded to pytest. Positional path arguments override the default
|
|
# discovery root (tests/).
|
|
|
|
set -uo pipefail
|
|
|
|
# ── Locate repo root ────────────────────────────────────────────────────────
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
REPO_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
|
|
|
|
# ── Locate python ───────────────────────────────────────────────────────────
|
|
# Probe local venvs first; fall back to the Nix devShell's editable venv
|
|
# (HERMES_PYTHON is exported by the devShell hook and ships [dev] extras:
|
|
# pytest, pytest-asyncio, pytest-xdist).
|
|
#
|
|
# A candidate must have pytest INSTALLED, not merely exist. The release venv
|
|
# at ~/.hermes/hermes-agent/venv has bin/activate but no pytest, so an
|
|
# existence-only probe selected it in checkouts/worktrees without a local
|
|
# .venv — every file then died with "No module named pytest" and the run
|
|
# reported "0 tests passed" (which reads green at a glance even though the
|
|
# exit code is 1). Skip such a venv and keep probing instead.
|
|
VENV=""
|
|
VENV_PYTHON=""
|
|
SKIPPED_VENVS=""
|
|
for candidate in "$REPO_ROOT/.venv" "$REPO_ROOT/venv" "$HOME/.hermes/hermes-agent/venv"; do
|
|
if [ -f "$candidate/bin/activate" ]; then
|
|
if "$candidate/bin/python" -c 'import pytest' 2>/dev/null; then
|
|
VENV="$candidate"
|
|
VENV_PYTHON="$candidate/bin/python"
|
|
break
|
|
fi
|
|
SKIPPED_VENVS="$SKIPPED_VENVS $candidate"
|
|
elif [ -f "$candidate/Scripts/activate" ]; then
|
|
if "$candidate/Scripts/python.exe" -c 'import pytest' 2>/dev/null; then
|
|
VENV="$candidate"
|
|
VENV_PYTHON="$candidate/Scripts/python.exe"
|
|
break
|
|
fi
|
|
SKIPPED_VENVS="$SKIPPED_VENVS $candidate"
|
|
fi
|
|
done
|
|
if [ -z "$VENV_PYTHON" ]; then
|
|
if [ -n "${HERMES_PYTHON:-}" ] && "${HERMES_PYTHON}" -c 'import pytest' 2>/dev/null; then
|
|
VENV_PYTHON="$HERMES_PYTHON"
|
|
else
|
|
echo "✗ No venv with pytest found. Install dev extras:" >&2
|
|
echo " uv sync --extra dev" >&2
|
|
if [ -n "$SKIPPED_VENVS" ]; then
|
|
echo " (skipped for missing pytest:$SKIPPED_VENVS — install dev extras there, or create $REPO_ROOT/.venv)" >&2
|
|
fi
|
|
exit 1
|
|
fi
|
|
fi
|
|
PYTHON="$VENV_PYTHON"
|
|
|
|
# ── Split args: our -j/--jobs vs pytest passthrough ─────────────────────────
|
|
N="${HERMES_TEST_WORKERS:-auto}"
|
|
PYTEST_ARGS=()
|
|
while [ $# -gt 0 ]; do
|
|
case "$1" in
|
|
-j|--jobs)
|
|
N="$2"; shift 2 ;;
|
|
-j*)
|
|
N="${1#-j}"; shift ;;
|
|
--jobs=*)
|
|
N="${1#--jobs=}"; shift ;;
|
|
*)
|
|
PYTEST_ARGS+=("$1"); shift ;;
|
|
esac
|
|
done
|
|
|
|
# ── Windows location variables (computed before we drop env) ───────────────
|
|
# `env -i` forwards HOME, which is enough on POSIX. Native Windows CPython
|
|
# resolves Path.home() from USERPROFILE (or HOMEDRIVE+HOMEPATH), stdlib
|
|
# platform paths come from LOCALAPPDATA/APPDATA, ssl/sockets need SYSTEMROOT,
|
|
# and tempfile needs TEMP/TMP. Dropping them breaks collection on native
|
|
# Windows (issues #67385, #70813). These are location variables, not
|
|
# credentials, so forwarding them keeps the isolation intent intact. Each is
|
|
# only forwarded when actually set, so POSIX runs are byte-for-byte unchanged.
|
|
WIN_ENV=()
|
|
for _win_var in USERPROFILE HOMEDRIVE HOMEPATH LOCALAPPDATA APPDATA SYSTEMROOT TEMP TMP; do
|
|
if [ -n "${!_win_var:-}" ]; then
|
|
WIN_ENV+=("$_win_var=${!_win_var}")
|
|
fi
|
|
done
|
|
|
|
# ── Live-gateway plugin (computed before we drop env) ───────────────────────
|
|
EXTRA_PYTHONPATH=""
|
|
EXTRA_PYTEST_PLUGINS=""
|
|
if [ -f "$HOME/.hermes/pytest_live_guard.py" ]; then
|
|
EXTRA_PYTHONPATH="$HOME/.hermes"
|
|
EXTRA_PYTEST_PLUGINS="pytest_live_guard"
|
|
fi
|
|
|
|
# ── Test-runner knobs (computed before we drop env) ──────────────────────────
|
|
# * HERMES_TEST_IMAGE is read by tests/docker/conftest.py to skip its
|
|
# session-scoped `docker build`. CI's docker.yml sets it to the image
|
|
# the build step just loaded; stripping it made every pytest subprocess
|
|
# rebuild the 5GB image from a cold builder cache instead (~4 min per
|
|
# worker per run, and the rebuilt image lacked the HERMES_GIT_SHA
|
|
# build-arg the workflow bakes in).
|
|
#
|
|
# These are test-infrastructure knobs, not credentials — same class as the
|
|
# HERMES_RUN_SLOW_PET_TESTS / HERMES_E2E_BROWSER opt-ins already forwarded.
|
|
# Keep this an explicit allowlist (no HERMES_TEST_* glob) so the "no
|
|
# credential can leak" property stays auditable at a glance.
|
|
TEST_ENV=()
|
|
for _test_var in HERMES_TEST_IMAGE; do
|
|
if [ -n "${!_test_var:-}" ]; then
|
|
TEST_ENV+=("$_test_var=${!_test_var}")
|
|
fi
|
|
done
|
|
|
|
# ── Run in hermetic env ──────────────────────────────────────────────────────
|
|
# env -i: start with empty environment, opt-in only what we need.
|
|
# No credential var can leak — you'd have to explicitly add it here.
|
|
echo "▶ running pytest-xdist (-n $N --dist loadfile)"
|
|
echo " (TZ=UTC LANG=C.UTF-8 PYTHONHASHSEED=0; clean env)"
|
|
|
|
cd "$REPO_ROOT"
|
|
|
|
# ── Pre-compile .pyc bytecode cache ─────────────────────────────────────────
|
|
# xdist workers import the same modules; pre-building the bytecode cache once
|
|
# here avoids every worker compiling on first import.
|
|
echo "▶ pre-compiling bytecode cache"
|
|
"$PYTHON" -m compileall -q -j 0 -- $(git ls-files '*.py') >/dev/null 2>&1 || true
|
|
|
|
echo "▶ pytest -n $N --dist loadfile"
|
|
exec env -i \
|
|
PATH="$PATH" \
|
|
HOME="$HOME" \
|
|
${WIN_ENV[@]+"${WIN_ENV[@]}"} \
|
|
${TEST_ENV[@]+"${TEST_ENV[@]}"} \
|
|
TZ=UTC \
|
|
LANG=C.UTF-8 \
|
|
LC_ALL=C.UTF-8 \
|
|
PYTHONHASHSEED=0 \
|
|
PYTHONUTF8=1 \
|
|
${HERMES_RUN_SLOW_PET_TESTS:+HERMES_RUN_SLOW_PET_TESTS="$HERMES_RUN_SLOW_PET_TESTS"} \
|
|
${HERMES_E2E_BROWSER:+HERMES_E2E_BROWSER="$HERMES_E2E_BROWSER"} \
|
|
${EXTRA_PYTHONPATH:+PYTHONPATH="$EXTRA_PYTHONPATH"} \
|
|
${EXTRA_PYTEST_PLUGINS:+PYTEST_PLUGINS="$EXTRA_PYTEST_PLUGINS"} \
|
|
"$PYTHON" -m pytest -n "$N" --dist loadfile -p no:cacheprovider \
|
|
-m "not integration" -q --tb=line \
|
|
${PYTEST_ARGS[@]+"${PYTEST_ARGS[@]}"}
|